Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4944 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3483. Min Act: -0.0000

Data Index: 379285 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1431334 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3309. Min Act: -0.0000

Data Index: 437249 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3085. Min Act: -0.0000

Data Index: 582115 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3286. Min Act: -0.0000

Data Index: 981974 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3365. Min Act: -0.0000

Data Index: 595072 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1064626 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3313. Min Act: -0.0000

Data Index: 393877 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1257245 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1048579 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3185. Min Act: -0.0000

Data Index: 621161 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3024. Min Act: -0.0000

Data Index: 709997 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1385931 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3213. Min Act: -0.0000

Data Index: 280612 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.2929. Min Act: -0.0000

Data Index: 752808 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1646393 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3153. Min Act: -0.0000

Data Index: 35611 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3023. Min Act: -0.0000

Data Index: 288747 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3015. Min Act: -0.0000

Data Index: 261143 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.3483. Min Range: -0.3483

Max Act: 0.3033. Min Act: -0.0000

Data Index: 686950 (C4 (Web Text))

Max Activating Token Index: 188